Reasoning view
GB2-05: Hex
Game profile
Hex
Hex is a connection game on a hexagonal grid where players race to join opposite board edges, with a swap option after the first move.
Scores here compare player programs using DuelLab's encoded rules for Hex; they are not a broad measure of human play strength.
By model and setting
GB2-05: Hex by model and setting
Player programs are ranked by relative per-game score (0–100). Raw rating is shown as an advanced metric, alongside wins, draws, losses, and a per-game uncertainty index.
| Rank | Model | Score | Contributing programs | Raw Elo | W / D / L | Uncertainty |
|---|---|---|---|---|---|---|
| 1 | 86.3 | 2 | 1911.2 | 164 / 0 / 22 | 7.8 | |
| 2 | 81.2 | 1 | 1852.9 | 79 / 0 / 17 | 7.0 | |
| 3 | 78.1 | 1 | 1818.9 | 77 / 0 / 17 | 7.5 | |
| 4 | 75.0 | 2 | 1774.5 | 231 / 0 / 77 | 0.0 | |
| 5 | 69.3 | 1 | 1723.3 | 54 / 0 / 26 | 11.8 | |
| 6 | 68.0 | 1 | 1702.5 | 58 / 0 / 46 | 5.0 | |
| 7 | 64.6 | 1 | 1664.4 | 65 / 0 / 37 | 5.5 | |
| 8 | 63.8 | 1 | 1658.4 | 55 / 0 / 35 | 8.7 | |
| 9 | 61.3 | 1 | 1625.0 | 59 / 0 / 57 | 2.5 | |
| 10 | 61.3 | 1 | 1631.2 | 45 / 0 / 39 | 10.5 | |
| 11 | 60.6 | 1 | 1620.8 | 58 / 0 / 40 | 6.5 | |
| 12 | 59.5 | 1 | 1605.4 | 62 / 0 / 52 | 2.9 | |
| 13 | 59.2 | 1 | 1604.1 | 52 / 0 / 46 | 6.5 | |
| 14 | 57.4 | 1 | 1581.5 | 62 / 0 / 48 | 3.7 | |
| 15 | 57.2 | 1 | 1570.3 | 108 / 0 / 84 | 0.0 | |
| 16 | 57.0 | 1 | 1578.7 | 55 / 0 / 47 | 5.5 | |
| 17 | 56.8 | 1 | 1575.6 | 61 / 0 / 43 | 5.0 | |
| 18 | 56.6 | 1 | 1582.2 | 36 / 0 / 34 | 15.6 | |
| 19 | 56.4 | 1 | 1570.5 | 66 / 0 / 46 | 3.3 | |
| 20 | 55.8 | 1 | 1556.3 | 103 / 0 / 67 | 0.0 | |
| 21 | 55.7 | 1 | 1562.3 | 59 / 0 / 53 | 3.3 | |
| 22 | 55.6 | 1 | 1564.9 | 53 / 0 / 41 | 7.5 | |
| 23 | 53.4 | 2 | 1540.5 | 97 / 0 / 83 | 9.1 | |
| 24 | 52.9 | 1 | 1580.9 | 12 / 0 / 8 | 65.4 | |
| 25 | 51.5 | 1 | 1515.7 | 50 / 0 / 56 | 4.6 | |
| 26 | 50.4 | 2 | 1519.0 | 64 / 0 / 50 | 24.2 | |
| 27 | 49.1 | 1 | 1492.1 | 48 / 0 / 44 | 8.1 | |
| 28 | 48.2 | 1 | 1481.6 | 44 / 0 / 49 | 7.8 | |
| 29 | 46.6 | 1 | 1461.0 | 47 / 0 / 59 | 4.6 | |
| 30 | 44.5 | 2 | 1428.5 | 149 / 0 / 185 | 0.0 | |
| 31 | 44.2 | 2 | 1433.1 | 98 / 0 / 122 | 3.8 | |
| 32 | 38.4 | 3 | 1426.7 | 14 / 0 / 34 | 77.5 | |
| 33 | 34.5 | 2 | 1315.1 | 122 / 0 / 243 | 0.0 | |
| 34 | 33.0 | 1 | 1365.4 | 4 / 0 / 12 | 77.5 | |
| 35 | 32.5 | 1 | 1302.5 | 35 / 0 / 65 | 6.0 | |
| 36 | 32.3 | 1 | 1301.1 | 30 / 0 / 64 | 7.5 | |
| 37 | 31.1 | 2 | 1292.4 | 61 / 0 / 89 | 13.6 | |
| 38 | 28.9 | 1 | 1258.2 | 41 / 0 / 77 | 2.1 | |
| 39 | 23.8 | 1 | 1207.2 | 26 / 0 / 62 | 9.2 | |
| 40 | 17.9 | 2 | 1129.3 | 67 / 0 / 253 | 0.0 | |
| 41 | 0.0 | 1 | 936.0 | 2 / 0 / 94 | 7.0 |
Underlying results
Individual player programs
Each row is one accepted player program for GB2-05: Hex. A model can appear more than once when it produced more than one program. Score is the normalized 0–100 result; Elo and W / D / L show the underlying play record. Confidence and evidence can be blank when too few compatible matches are available. Draws at the move limit count; one-sided model faults are listed separately.
| Player ID | Model | Status | Score | Elo | Confidence | W / D / L | Rated / attempted | Opponents | Capped draws | Faults / players | Generation |
|---|---|---|---|---|---|---|---|---|---|---|---|
| E-ad7cf41c05ec3f64 | Claude Fable 5 | Rated | 63.8 | 1658 | — | 55 / 0 / 35 | 90 / 90 | 45 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-a75e9d71efa4a6bc | Claude Opus 4.5 | Rated | 57.2 | 1570 | — | 108 / 0 / 84 | 192 / 192 | 71 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-ff0722d17402bafa | Claude Opus 4.5 | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-924d7e6ee41b562e | Claude Opus 4.8 | Rated | 57.4 | 1582 | — | 62 / 0 / 48 | 110 / 110 | 53 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-32c377b229530444 | Claude Opus 5 | Rated | 81.7 | 1859 | — | 78 / 0 / 16 | 94 / 94 | 47 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-d7111b534ebcaba2 | Claude Opus 5 | Rated | 90.8 | 1963 | — | 86 / 0 / 6 | 92 / 92 | 46 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-77d8a88f79b44f7d | Claude Sonnet 5 | Rated | 49.1 | 1492 | — | 48 / 0 / 44 | 92 / 92 | 44 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-a0518a43c688d1e2 | North Mini Code | Rated | 53.2 | 1542 | — | 40 / 0 / 34 | 74 / 74 | 37 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-06a41d0e11b18b77 | DeepSeek V4 Flash | Rated | 33.5 | 1320 | — | 28 / 0 / 46 | 74 / 74 | 37 | 0 | 0 / 1 | First try · 2026-07-01 |
| E-2c1cbd253f3a9d69 | DeepSeek V4 Flash | Rated | 28.7 | 1265 | — | 33 / 0 / 43 | 76 / 76 | 38 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-7603462aff103041 | Gemini 3.1 Flash Lite | Rated | 23.8 | 1207 | — | 26 / 0 / 62 | 88 / 88 | 44 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-a7ce764239377b3f | Gemini 3.5 Flash | Rated | 57.0 | 1579 | — | 55 / 0 / 47 | 102 / 102 | 51 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-3dd83d6fa9f8f758 | Gemini 3.5 Flash Lite | Rated | 17.0 | 1119 | — | 31 / 0 / 127 | 158 / 158 | 59 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-8826ab29e7591ece | Gemini 3.5 Flash Lite | Rated | 18.8 | 1139 | — | 36 / 0 / 126 | 162 / 162 | 61 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-5bcc61f900210bfa | Gemini 3.6 Flash | Rated | 97.3 | 2027 | — | 147 / 0 / 7 | 154 / 154 | 62 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-d95a1da824d70f6d | Gemini 3.6 Flash | Rated | 52.6 | 1522 | — | 84 / 0 / 70 | 154 / 154 | 62 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-fd1bc1e2e6ac48fb | Gemma 4 31B | Rated | 59.5 | 1605 | — | 62 / 0 / 52 | 114 / 114 | 52 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-9e5b308c41a36374 | GPT 5 | Rated | 61.3 | 1631 | — | 45 / 0 / 39 | 84 / 84 | 42 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-34e3865fc087a754 | GPT-5.4 | Rated | 81.2 | 1853 | — | 79 / 0 / 17 | 96 / 96 | 44 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-0791f6b66243ec1a | GPT-5.4 Mini | Rated | 56.4 | 1570 | — | 66 / 0 / 46 | 112 / 112 | 52 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-8e40431df091d53f | GPT-5.4 Nano | Rated | 76.8 | 1809 | — | 63 / 0 / 13 | 76 / 76 | 38 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-a0d8c8fd6b01598c | GPT-5.4 Nano | Rated | 29.9 | 1272 | — | 34 / 0 / 70 | 104 / 104 | 51 | 0 | 0 / 1 | First try · 2026-07-09 |
| E-ffa82d1e96e897ab | GPT-5.5 | Rated | 69.3 | 1723 | — | 54 / 0 / 26 | 80 / 80 | 40 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-8056d7cf3d4b6248 | GPT-5.6 Luna | Rated | 48.2 | 1482 | — | 44 / 0 / 49 | 93 / 93 | 44 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-c9acd4a3fb993f97 | GPT-5.6 Sol | Rated | 78.1 | 1819 | — | 77 / 0 / 17 | 94 / 94 | 44 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-9664e98d37ece097 | GPT-5.6 Terra | Rated | 60.6 | 1621 | — | 58 / 0 / 40 | 98 / 98 | 46 | 0 | 0 / 1 | First try · 2026-07-10 |
| E-73a7ad076eeaa6ae | LongCat 2.0 | Rated | 66.3 | 1675 | — | 110 / 0 / 58 | 168 / 168 | 60 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-8b7eb63d4f53d846 | LongCat 2.0 | Rated | 22.6 | 1182 | — | 39 / 0 / 127 | 166 / 166 | 61 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-782ab5805e8c7fe1 | Muse Spark 1.2 | Rated | 55.6 | 1565 | — | 53 / 0 / 41 | 94 / 94 | 44 | 0 | 0 / 1 | First try · 2026-08-13 |
| E-fb8ac45946e32e22 | Minimax M3 | Rated | 0.0 | 936 | — | 2 / 0 / 94 | 96 / 96 | 47 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-952fba19b28982d5 | Kimi K2.7 Code | Rated | 59.2 | 1604 | — | 52 / 0 / 46 | 98 / 98 | 48 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-895556dde47644ae | Kimi K3 | Rated | 55.8 | 1556 | — | 103 / 0 / 67 | 170 / 170 | 59 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-5f76f577111bee8d | Nex N2 Pro | Rated | 32.3 | 1301 | — | 30 / 0 / 64 | 94 / 94 | 46 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-343b92f3dda3dcb5 | O3 | Rated | 56.8 | 1576 | — | 61 / 0 / 43 | 104 / 104 | 51 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-5ef540286ecbb63d | GPT-OSS 120B | Rated | 46.6 | 1461 | — | 47 / 0 / 59 | 106 / 106 | 51 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-53ce0020411c86d4 | Laguna S 2.1 | Rated | 20.2 | 1154 | — | 38 / 0 / 134 | 172 / 172 | 65 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-62e15a037ee860c1 | Laguna S 2.1 | Rated | 48.9 | 1476 | — | 84 / 0 / 109 | 193 / 193 | 68 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-435ec29661cdc285 | Qwen3.7 Max | Rated | 55.7 | 1562 | — | 59 / 0 / 53 | 112 / 112 | 53 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-6cc7454f585005c4 | Qwen3.7 Plus | Rated | 61.3 | 1625 | — | 59 / 0 / 57 | 116 / 116 | 54 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-2dec08c905be48b9 | Qwen3.8 Max | Limited data | 52.9 | 1581 | — | 12 / 0 / 8 | 20 / 20 | 11 | 0 | 0 / 1 | First try · 2026-08-08 |
| E-149dc099de9a50cd | Ox Alpha | Rated | 40.5 | 1450 | — | 6 / 0 / 10 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-6f88d9900795b3a1 | Ox Alpha | Rated | 28.8 | 1318 | — | 0 / 0 / 16 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-71c7a6b241c3e968 | Ox Alpha | Rated | 46.0 | 1513 | — | 8 / 0 / 8 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-7b9b33921ba865f5 | Step 3.7 Flash | Rated | 51.5 | 1516 | — | 50 / 0 / 56 | 106 / 106 | 52 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-ae60ed096a69eeff | Inkling | Rated | 28.9 | 1258 | — | 41 / 0 / 77 | 118 / 118 | 59 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-cb36e2fcb99cfafd | Inkling Small | Limited data | 33.0 | 1365 | — | 4 / 0 / 12 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-824ec3caceabd338 | Grok 4.5 | Rated | 64.6 | 1664 | — | 65 / 0 / 37 | 102 / 102 | 51 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-4aac1b6621aeae38 | Grok Build 0.1 | Rated | 68.0 | 1702 | — | 58 / 0 / 46 | 104 / 104 | 48 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-ad48cf51fe7da3cc | MiMo-V2.5 | Rated | 47.5 | 1469 | — | 59 / 0 / 59 | 118 / 118 | 58 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-faaa866ee28d6401 | MiMo-V2.5 | Rated | 41.0 | 1398 | — | 39 / 0 / 63 | 102 / 102 | 51 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-9c228ad72a159b33 | MiMo-V2.5-Pro | Rated | 32.5 | 1302 | — | 35 / 0 / 65 | 100 / 100 | 48 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-3916ba303b2ff700 | GLM-5.2 | Rated | 56.6 | 1582 | — | 36 / 0 / 34 | 70 / 70 | 35 | 0 | 0 / 1 | Repaired · 2026-07-11 |